Skip to main content
Log in

An evaluation oftcp with explicit congestion notification

Évaluation du protocole TCP en présence d’une notification explicite d’encombrement (ECN)

  • Published:
Annales des Télécommunications Aims and scope Submit manuscript

Abstract

We study the effect of Explicit Congestion Notification (ecn) ontcp for relatively large but finite file transfers inip networks, and compare it to other congestion avoidance mechanisms, namely Drop Tail (dt) and Random Early Detection (red). We use simulation to measuretcp performance for transfers initiated by a varying number of end hosts. In contrast to previous work, we focus on situations in which all nodes in the network operate uniformly under the same mechanism (dt orred orecn). Our results show that under such uniform conditionsecn does not necessarily lead to significant improvement intcp goodput, although in no case does it lead to an actual degradation in performance. Our results also show that, withecn, tcp flows benefit from lower overhead for unsuccessful transmissions. Furthermore, lockouts are largely avoided. In other words, in an all-ecn network resources are shared more fairly. Finally, we show that global synchronization is no longer an issue, and argue that currenttcp versions have essentially solved the problem, regardless of the queue management scheme employed.

Résumé

L’article étudie l’effet d’une notification explicite d’encombrement (ecn) sur le protocoletcp pour des transferts de fichiers relativement grands mais finis dans les réseauxip et le compare à d’autres mécanismes d’évitement d’encombrement, à savoir le rejet du dernier arrivé (dt) et la détection précoce aléatoire (red). Une simulation sert à mesurer la performance du protocoletcp pour des transferts déclenchés par un nombre variable d’hôtes terminaux. Contrairement à un travail antérieur, l’article traite ces situations à tous les noeuds du réseau fonctionnant uniformément selon le même mécanisme (dt, red ouecn). Les résultats montrent que sous ces conditions d’uniformité,ecn ne conduit pas nécessairement à une amélioration sensible du débit utile, bien qu’en aucun cas il n’entraîne de dégradation. Les résultats montrent aussi que, avececn, le fluxtcp bénéficie d’un surcoût de gestion plus faible pour les transmissions infructueuses. De plus, les blocages sont largement évités. Autrement dit, dans un réseau toutecn, les ressources sont partagées plus équitablement. On montre enfin qu’une synchronisation globale n’est plus un problème et que les versionstcp actuelles ont pour l’essentiel résolu le problème, quel que soit le schéma de gestion de la file d’attente employé.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Postel (J. B.), Transmission Control Protocol,rfc 793, September 1981.

  2. Braden (R.), Requirements for Internet Hosts — Communication Layers,rfc 1122, October 1989.

  3. Jocobson (V.),Braden (R.),Borman (D.),tcp Extensions for High Performance,rfc 1323, May 1992.

  4. Nagle (J.), Congestion Control inip/tcp Internetworks,rfc 896, January 1984.

  5. Nielsen (H. F.),Gettys (J.),Baird-Smith (A.),Prud’hommeaux (E.),Lie (H.),Lilley (C.), “Network Performance Effects ofhttp/1.1,css1, andpng”,Proceedings ofacm sigcomm’97, Cannes, France, September 1997.

  6. Allman (M.),Paxson (V.),Stevens (W. R.),tcp Congestion Control,rfc 2581, April 1999.

  7. Mathis (M.),Mahdavi (J.),Floyd (S.),Romanow (A.),tcp Selective Acknowledgment Options,rfc 2018, April 1996.

  8. Braden (B.)et al., Recommendations on Queue Management and Congestion Avoidance,rfc 2309, April 1998.

  9. Desimone (A.),Chuah (M. C.),Yue (O. C.), “Throughput Performance of Transport-Layer Protocols over Wirelesslans”, inProceedings ofglobecom’93, December 1993.

  10. Ramakrishnan (K.K.),Floyd (S.),Black (S.), The Addition of Explicit Congestion Notification (ecn) toip, rfc 3168, September 2001.

  11. Bradner (S.), The Internet Standards Process — Revision 3,rfc 2026, October 1996.

  12. Floyd (S.),Jacobson (V.), “Random Early Detection Gateways for Congestion Avoidance”,acm/ieeeTransactions on Networking, 3(1), August 1993.

  13. Cisco Systems, Ciscoios Release 12.2(8)T User’s Manual, February 2002.

  14. Pentikousis (K.),Badr (H.),Kharmah (B.), “On the Performance Gains oftcp withecn”,Proceedings of the 2ndEuropean Conference on Universal Multiservice Networks (ecumn2002), Colmar, France, April 2002.

  15. Ramakrishnan (K.),Jain (R.), “A Binary Feedback Mechanism for Congestion Avoidance in Computer Networks”,acmTransactions on Computer Systems, 8(2), May 1990.

  16. Stallings (W.),isdn and Broadbandisdn, with France Relay andatm, Fourth Edition,Prentice Hall, October 1998.

  17. May (M.),Bolot (J.),Diot (C.),Lyles (B.), “Reasons Not to Deployred”,Proceedings of 7th International Workshop on Quality of Service (iwqoS’99), London, June 1999.

  18. Christiansen (M.),Jeffay (K.),Ott (D.),Smith (F. D.), “Tuningred for Web Traffic”,Proceedings ofacm sigcomm2000, Stockholm, Sweden, August 2000.

  19. Slim (J. H.),Ahmed (U.), Performance Evaluation of Explicit Congestion Notification (ecn) inip Networks, RFC 2884, July 2000.

  20. Zhang (Y.),Qiu (L.), “Understanding the End-to-End Impact ofred in a Heterogeneous Environment”, Cornell CS Technical Report 2000-1802, July 2000.

  21. Floyd (S.), “tcp and Explicit Congestion Notification”,acmComputer Communication Review, 24(5), October 1994, pp. 10–23.

  22. Athuraliya (S.),Li (V.),Low (S.),Yin (Q.), “rem: Active Queue Management”,ieeeNetwork, May/June 2001.

  23. Pentikousis (K.), “tcp in wired-cum-wireless environments”,ieeeCommunications Surveys, 3(4), Fourth Quarter 2000.

  24. Pentikousis (K.),Badr (H.), “On the Resource Efficiency of Explicit Congestion Notification”,Proceedings ofnetworking2002, Pisa, Italy, May 2002.

  25. UCB/LBNL/VINT Network Simulator — ns (version 2), 〈http://www.isi.edu/nsnam/ns〉 (June 2003).

  26. Zhang (L.),Clark (D. D.), “Oscillating behavior of network traffic: A case study simulation”,Internetworking: Research and Experience, 1(2), December 1990.

  27. End-to-end mailing list archive, 〈ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail〉 (June 2003).

  28. Floyd (S.),red: Discussions of Setting Parameters, 〈http://www.aciri.org/floyd/redparameters.txt〉 (June 2003).

  29. Zhang (L.),Shenker (S.),Clark (D. D.), “Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two-Way Traffic”,Proceedings ofsigcomm91, Zurich, Switzerland, September 1991.

  30. May (M.),Bonald (T.),Bolot (J.-C.), “Analytic Evaluation ofred Performance”,Proceedings ofieee infocom2000, Tel-Aviv, Israel, March 2000.

  31. Qiu (L.),Zhang (Y.),Keshav (S.), “On Individual and Aggregatetcp Performance”,Proceedings oficnp1999, Toronto, Canada, October 1999.

  32. Allman (M.), “On the Generation and Use oftcp Acknowledgements”,acmComputer Communications Review, 28(5), October 1998.

  33. Floyd (S.),Henderson (T.), The NewReno Modification totcp’s Fast Recovery Algorithm,rfc 2582, April 1999.

  34. Jain (R.),Chiu (D.),Hawe (W.), “A Quantitative Measure of Fairness and Discrimination for Resource Allocation in Shared Computer Systems”,dec Research Report TR-301, September 1984.

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Kostas Pentikousis.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Pentikousis, K., Badr, H. An evaluation oftcp with explicit congestion notification. Ann. Télécommun. 59, 170–198 (2004). https://doi.org/10.1007/BF03179680

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03179680

Key words

Mots clés

Navigation